architecture: CascadeRCNN
max_iters: 270000
snapshot_iter: 30000
use_gpu: true
log_smooth_window: 20
log_iter: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_ssld_pretrained.tar
weights: output/cascade_rcnn_dcn_r101_vd_fpn_3x_server_side/model_final
metric: COCO
num_classes: 81

CascadeRCNN:
  backbone: ResNet
  fpn: FPN
  rpn_head: FPNRPNHead
  roi_extractor: FPNRoIAlign
  bbox_head: CascadeBBoxHead
  bbox_assigner: CascadeBBoxAssigner

ResNet:
  norm_type: bn
  depth: 101
  feature_maps: [2, 3, 4, 5]
  freeze_at: 2
  variant: d
  dcn_v2_stages: [3, 4, 5]
  lr_mult_list: [0.05, 0.05, 0.1, 0.15]

FPN:
  max_level: 6
  min_level: 2
  num_chan: 64
  spatial_scale: [0.03125, 0.0625, 0.125, 0.25]

FPNRPNHead:
  anchor_generator:
    anchor_sizes: [32, 64, 128, 256, 512]
    aspect_ratios: [0.5, 1.0, 2.0]
    stride: [16.0, 16.0]
    variance: [1.0, 1.0, 1.0, 1.0]
  anchor_start_size: 32
  min_level: 2
  max_level: 6
  num_chan: 64
  rpn_target_assign:
    rpn_batch_size_per_im: 256
    rpn_fg_fraction: 0.5
    rpn_positive_overlap: 0.7
    rpn_negative_overlap: 0.3
    rpn_straddle_thresh: 0.0
  train_proposal:
    min_size: 0.0
    nms_thresh: 0.7
    pre_nms_top_n: 2000
    post_nms_top_n: 2000
  test_proposal:
    min_size: 0.0
    nms_thresh: 0.7
    pre_nms_top_n: 500
    post_nms_top_n: 300

FPNRoIAlign:
  canconical_level: 4
  canonical_size: 224
  min_level: 2
  max_level: 5
  box_resolution: 7
  sampling_ratio: 2

CascadeBBoxAssigner:
  batch_size_per_im: 512
  bbox_reg_weights: [10, 20, 30]
  bg_thresh_lo: [0.0, 0.0, 0.0]
  bg_thresh_hi: [0.5, 0.6, 0.7]
  fg_thresh: [0.5, 0.6, 0.7]
  fg_fraction: 0.25

CascadeBBoxHead:
  head: CascadeTwoFCHead
  bbox_loss: BalancedL1Loss
  nms:
    keep_top_k: 100
    nms_threshold: 0.5
    score_threshold: 0.05

BalancedL1Loss:
  alpha: 0.5
  gamma: 1.5
  beta: 1.0
  loss_weight: 1.0

CascadeTwoFCHead:
  mlp_dim: 1024

LearningRate:
  base_lr: 0.02
  schedulers:
  - !PiecewiseDecay
    gamma: 0.1
    milestones: [180000, 240000]
  - !LinearWarmup
    start_factor: 0.1
    steps: 1000

OptimizerBuilder:
  optimizer:
    momentum: 0.9
    type: Momentum
  regularizer:
    factor: 0.0001
    type: L2

TrainReader:
  inputs_def:
    fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd']
  dataset:
    !COCODataSet
    image_dir: train2017
    anno_path: annotations/instances_train2017.json
    dataset_dir: dataset/coco
  sample_transforms:
  - !DecodeImage
    to_rgb: true
  - !RandomFlipImage
    prob: 0.5
  - !AutoAugmentImage
    autoaug_type: v1
  - !NormalizeImage
    is_channel_first: false
    is_scale: true
    mean: [0.485,0.456,0.406]
    std: [0.229, 0.224,0.225]
  - !ResizeImage
    target_size: [640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024]
    max_size: 1500
    interp: 1
    use_cv2: true
  - !Permute
    to_bgr: false
    channel_first: true
  batch_transforms:
  - !PadBatch
    pad_to_stride: 32
    use_padded_im_info: false
  batch_size: 2
  shuffle: true
  worker_num: 2
  use_process: false

EvalReader:
  inputs_def:
    fields: ['image', 'im_info', 'im_id', 'im_shape']
    # for voc
    #fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
  dataset:
    !COCODataSet
    image_dir: val2017
    anno_path: annotations/instances_val2017.json
    dataset_dir: dataset/coco
  sample_transforms:
  - !DecodeImage
    to_rgb: true
    with_mixup: false
  - !NormalizeImage
    is_channel_first: false
    is_scale: true
    mean: [0.485,0.456,0.406]
    std: [0.229, 0.224,0.225]
  - !ResizeImage
    interp: 1
    max_size: 13330
    target_size: 800
    use_cv2: true
  - !Permute
    channel_first: true
    to_bgr: false
  batch_transforms:
  - !PadBatch
    pad_to_stride: 32
    use_padded_im_info: true
  batch_size: 1
  shuffle: false
  drop_empty: false
  worker_num: 2

TestReader:
  inputs_def:
    # set image_shape if needed
    fields: ['image', 'im_info', 'im_id', 'im_shape']
  dataset:
    !ImageFolder
    anno_path: annotations/instances_val2017.json
  sample_transforms:
  - !DecodeImage
    to_rgb: true
    with_mixup: false
  - !NormalizeImage
    is_channel_first: false
    is_scale: true
    mean: [0.485,0.456,0.406]
    std: [0.229, 0.224,0.225]
  - !ResizeImage
    interp: 1
    max_size: 1333
    target_size: 800
    use_cv2: true
  - !Permute
    channel_first: true
    to_bgr: false
  batch_transforms:
  - !PadBatch
    pad_to_stride: 32
    use_padded_im_info: true
  batch_size: 1
  shuffle: false